Internet-based Morphable Model, Kemelmacher, ICCV 2013

Internet-based Morphable Model

Ira Kemelmacher-Shlizerman
Univ. of Washington

ICCV 2013

We present a method for building a morphable face model directly from photos on the Internet. Morphable models have shown very impressive results more than a decade ago, one of the major challenges, however, is to capture and register 3D laser scans of large number of faces and facial expressions. Nowadays, there are enormous amounts of face photos on the Internet, large portion of which has semantic labels. We propose a framework to build a morphable model directly from photos; our framework includes dense registration of Internet photos, as well as, new single view shape reconstruction and expression modification algorithms.





keywords:  single view face reconstruction, 3D, facial expression modification, facial expression reconstruction, faces, in the wild, Internet photos, computer, vision.


Files:

Spotlight  Paper   Video    Poster


Data

will upload soon (email me if you'd like it sooner!)


Citation:
Ira Kemelmacher-Shlizerman, "Internet-based Morphable Model", International Conference on Computer Vision (ICCV), 2013.

@article{kem:iccv13,
author = {Ira Kemelmacher-Shlizerman},
title = {Internet-based Morphable Model},
journal ={International Conference on Computer Vision (ICCV)},
year = {2013},
}


Acknowledgment
Thanks to Supasorn Suwajanakorn for helping create the videos.